© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 915
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    擀
    0.75
     अनी
    0.70
    médiaire
    0.69
    draggable
    0.69
     Hobson
    0.68
    挽
    0.67
     Kimura
    0.66
    حاب
    0.65
    िश्वत
    0.65
    嵇
    0.64
    POSITIVE LOGITS
     lights
    4.03
     lighting
    3.94
     Lighting
    3.67
     illumination
    3.67
     Lights
    3.63
     lamps
    3.63
    Lighting
    3.60
    灯
    3.57
    Lights
    3.50
    燈
    3.48
    Activations Density 1.858%

    No Known Activations